10 citations found. Retrieving documents...
L. Ardissono, G. Boella, and L. Lesmo, \Recognition of ProblemSolving Plans in Dialogue Interpretation," In Proceedings of the Fifth International Conference on User Modeling, pages 195-197, Kailua-Kona, Hawaii, January 1996.

 Home/Search   Document Details and Download   Summary   Related Articles   Check  

This paper is cited in the following contexts:
Retroactive Recognition of Interleaved Plans for Natural.. - Blaylock (2001)   (3 citations)  (Correct)

....xxx bonds. Their separation of discourse plans allows them to be able to recognize such speech act like phenomena at a multi utterance level. Ramshaw During the same period of Lambert, Ramshaw [Ram89b, Ram89a, Ram91] proposed a di#erently separated model (which was later extended by Ardissono [ABL96] Instead of a discourse level, Ramshaw proposed an exploration level. The intuition is that some utterances are made simply in the attempt to explore a possible course of action, whereas others are explicitly made to attempt to execute a plan. This model allows the system to distinguish ....

....request that actions be executed without first formulating a specific plan (such as sending an ambulance to a heart attack victim) Future plan recognition systems will need to be able to recognize and deal with these kinds of domains. Although Ramshaw and Ardissono s work [Ram89b, Ram89a, Ram91, ABL96] provide hints at how one might begin to structure such a solution, this problem has not yet been addressed by the literature. 6.4 Incremental Understanding Nearly all current dialogue systems operate at an utterance level of granularity. Human dialogue is very di#erent [Cla97] In human human ....

L. Ardissono, G. Boella, and L. Lesmo. Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii, 1996.


Retroactive Recognition of Interleaved Plans for Natural.. - Blaylock (2001)   (3 citations)  (Correct)

....xxx bonds. Their separation of discourse plans allows them to be able to recognize such speech act like phenomena at a multi utterance level. Ramshaw During the same period of Lambert, Ramshaw [Ram89b, Ram89a, Ram91] proposed a di erently separated model (which was later extended by Ardissono [ABL96] Instead of a discourse level, Ramshaw proposed an exploration level. The intuition is that some utterances are made simply in the attempt to explore a possible course of action, whereas others are explicitly made to attempt to execute a plan. This model allows the system to distinguish ....

....request that actions be executed without rst formulating a speci c plan (such as sending an ambulance to a heart attack victim) Future plan recognition systems will need to be able to recognize and deal with these kinds of domains. Although Ramshaw and Ardissono s work [Ram89b, Ram89a, Ram91, ABL96] provide hints at how one might begin to structure such a solution, this problem has not yet been addressed by the literature. 6.4 Incremental Understanding Nearly all current dialogue systems operate at an utterance level of granularity. Human dialogue is very di erent [Cla97] In human human ....

L. Ardissono, G. Boella, and L. Lesmo. Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195-197, Kailua-Kona, Hawaii, 1996.


Managing Communicative Intentions in Dialogue Using a.. - Blaylock (2002)   (Correct)

....dialogues are all of the master slave type ( Grosz and Sidner, 1990] where one agent is proactive in planning and the other basically serves as an information source. It is unclear if this model would be suitable for domains outside of information seeking dialogues. Ardissono et al. The work in [Ardissono et al. 1996] modified the work of Carberry et al. by generalizing the execution model. Instead of Domain, Problem solving, Discourse, the model became Goal, Problem solving, Action. The problem solving level consists of just two high level plans: Satisfy and Try execute. These decompose into an execution ....

....In order for an agent to Tryexecute an action, it first checks constraints and Satisfies them if necessary; it then verifies preconditions, does the action and checks the results. Utterances are explained based on some step in this execution model. For example, consider the following dialogue ([Ardissono et al. 1996]) Mark: Sell me a bottle of whiskey. Lucy: Are you over 18 Here, Lucy s response can be seen as her doing a Try execute of selling the whiskey, needing to know if Mark is over 18 in order to verify a constraint. The domain level is the same as other previous work. The action level, although ....

[Article contains additional citation context not shown here]

L. Ardissono, G. Boella, and L. Lesmo, "Recognition of ProblemSolving Plans in Dialogue Interpretation," In Proceedings of the Fifth International Conference on User Modeling, pages 195--197, Kailua-Kona, Hawaii, January 1996.


A Plan Based Agent Architecture for Interpreting Natural .. - Ardissono, Boella, Lesmo (2000)   (1 citation)  Self-citation (Ardissono Boella Lesmo)   (Correct)

....an experimental exam, which have different recipes: for instance, the latter contains the step of doing laboratory work. Actions are represented by means of the same formalism in the three plan libraries, so that the same procedures can be used to work and reason about them. There are four 11 In Ardissono et al. 1996), a preliminary version of the metalevel plans was introduced and it was referred to as Problem Solving library. 1) A generic action from the Domain library (Take university exam) name: Take university exam roles: agt, a, person) obj, ex, exam) constraints: enrolled(a, Turin university) ....

Ardissono, L., Boella, G. & Lesmo, L. (1996). Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii.


An agent model for NL dialog interfaces - Ardissono, Boella (1998)   Self-citation (Ardissono Boella)   (Correct)

....human human dialog, in order to interact with its users in a friendly way [8] This requires a major effort in understanding which intentions underly speech acts. In this paper, we describe our declarative, agent like architecture for modeling NL dialog, a preliminary version of which appeared on [4]. Our model has a two level, plan based representation of the knowledge about acting: at the metalevel, the Agent Modeling (AM) plans describe the rational intention driven behavior adopted by agents when they select and execute complex plans to reach their goals. At the object level, there are ....

L. Ardissono, G. Boella, and L. Lesmo. Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii, 1996.


A Plan-Based Model of Misunderstandings in Cooperative.. - Ardissono, Boella, Damiano (1998)   (4 citations)  Self-citation (Ardissono Boella)   (Correct)

....3.1 REPRESENTATION OF THE AGENT KNOWLEDGE ABOUT ACTING Our analysis of misunderstandings is performed in a plan based architecture for generating and recognizing agent behavior, based on a two level representation of the knowledge about acting. At the metalevel, the Agent Modeling (AM) library (Ardissono et al. 1996) describes the recipes for planning and executing actions; at the object level, there are the Domain and the Speech Act plan libraries, and some internal actions like those describing the interpretation task; the Domain library (Ardissono et al. 1993) describes the recipes for obtaining the domain ....

....3.1. 2 The metalevel actions The Agent Modeling (AM) actions take domain actions and speech acts as objects: the idea is that an agent who is performing a problem solving activity to obtain his goals can plan both domain and linguistic actions, according to what is better in the specific situation (Ardissono et al. 1996). Figure 1 shows a portion of the metalevel library: as it can be seen, most of the AM actions have a source parameter (denoted as s) that represents the agent for whom the action is performed (i.e. its beneficiary) When an agent acts on his own, this parameter is bound to the agent himself; in ....

[Article contains additional citation context not shown here]

L. Ardissono, G. Boella, & L. Lesmo (1996). Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii.


Piani per un'architettura di agente BDI - Ardissono, al   Self-citation (Ardissono Boella Lesmo)   (Correct)

....linguistiche che hanno la condizione tra i loro effetti (per esempio, chiedere ad un altro agente, o verificare da se ) poich e le azioni della libreria di dominio non sono ricorsive, non si generano istanze di piani di AM con rami infiniti. La costruzione della libreria di AM Come proposto in [2], il dialogo deve essere visto come una successione di turni la cui coerenza risiede nel fatto che il parlante, per mezzo di ciascun enunciato, sta perseguendo uno scopo che viene condiviso dai due interlocutori, oppure l enunciato e spiegabile come continuazione di uno dei suoi goal precedenti ....

....del passo di controllo di una precondizione all interno dell azione select feasible action nella libreria di AM. Conclusioni Il modello di agente qui proposto verr a utilizzato per estendere un sistema di consulenza automatica in un dominio ristretto, un dipartimento di informatica ([3, 1, 4, 2]) Di fronte alle richieste di un utente, il sistema deve collaborare attivamente, cercando non solo di soddisfare i goal che l interlocutore comunica ma anche fornendo informazioni supplementari per metterlo in grado di raggiungere i propri scopi nel modo migliore. In una prospettiva pi u ampia, ....

L. Ardissono, G. Boella, and L. Lesmo. Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii, 1996.


A Plan-Based Formalism to Express Knowledge About Actions - Ardissono, Boella, Lesmo (1997)   Self-citation (Ardissono Boella Lesmo)   (Correct)

.... domain (we chose the University domain as a testing domain [4] The Speech Act library describes the speech acts with particular attention to the direct and indirect approaches to communication and politeness techniques [2] The Agent Modeling library (AM library) has been introduced in [3] to represent problem solving behavior and will be described in detail later on. 4 All the libraries are organized on the basis of a decomposition and a generalization hierarchy [17] The former hierarchy specifies how a complex action can be performed by executing simpler actions. The latter ....

....a complex action can be performed by executing simpler actions. The latter supports feature inheritance among actions; it also allows to represent at a higher level of abstraction generic plans can be only partially specified, an action is the least specified plan associated with itself. 4 In [3], the AM library was referred to as Problem Solving library. actions, that can be associated to different behaviors according to the context in which they are executed. For example, the generic action that represents communicating with a professor can be specialized into an action for ....

L. Ardissono, G. Boella, and L. Lesmo. Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii, 1996.


Extending the Role of User Feedback in Plan Recognition and.. - Ardissono, Cohen (1996)   (3 citations)  Self-citation (Ardissono)   (Correct)

....to select a node as the basis of a clarifying question to the user, a criterion can be applied which seeks to eliminate the most fault partitions based on the user s reply, and thereby reduce the length of the clarification dialogue. In this paper, we focus on a model of plan recognition ([6, 5, 7, 2]; henceforward to be referred to as the ALS model) which explores the role of user modeling within plan recognition, and presents an architecture for plan recognition which indicates the stages at which user modeling can be applied, to improve the plan recognition process. The ALS model has a ....

L. Ardissono, G. Boella, and L. Lesmo. Recognition of problem-solving plans in dialogue interpretation. In Proc. 5th Int. Conf. on User Modeling, pages 195--197, Kailua-Kona, Hawaii, 1996.


Managing Communicative Intentions in Dialogue Using a.. - Blaylock (2002)   (Correct)

No context found.

L. Ardissono, G. Boella, and L. Lesmo, \Recognition of ProblemSolving Plans in Dialogue Interpretation," In Proceedings of the Fifth International Conference on User Modeling, pages 195-197, Kailua-Kona, Hawaii, January 1996.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC